理论 · learning theory论文趋势 2023–2026

学习理论及相关：learning_theory

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,350 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

理论 · learning theory论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202357245086
2024265106211393
20251061471324389
20261122001700482

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部理论 · learning theory论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,350 篇，第 13 / 27 页

  1. ICLR 2025Semialgebraic Neural Networks: From roots to representations
  2. ICLR 2025Separation Power of Equivariant Neural Networks
  3. ICLR 2025Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
  4. ICLR 2025Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees
  5. ICLR 2025State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
  6. ICLR 2025Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
  7. ICLR 2025Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs
  8. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
  9. ICLR 2025Strong Model Collapse
  10. ICLR 2025Task Descriptors Help Transformers Learn Linear Models In-Context
  11. ICLR 2025The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures
  12. ICLR 2025The Computational Complexity of Positive Non-Clashing Teaching in Graphs
  13. ICLR 2025The Foundations of Tokenization: Statistical and Computational Concerns
  14. ICLR 2025Theory on Mixture-of-Experts in Continual Learning
  15. ICLR 2025Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
  16. ICLR 2025Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization
  17. ICLR 2025Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification
  18. ICLR 2025Towards Understanding the Universality of Transformers for Next-Token Prediction
  19. ICLR 2025Tractable Multi-Agent Reinforcement Learning through Behavioral Economics
  20. ICLR 2025Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
  21. ICLR 2025Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
  22. ICLR 2025Transformer Learns Optimal Variable Selection in Group-Sparse Classification
  23. ICLR 2025Transformers are Universal In-context Learners
  24. ICLR 2025Transformers Handle Endogeneity in In-Context Linear Regression
  25. ICLR 2025Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
  26. ICLR 2025Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
  27. ICLR 2025Transformers Provably Solve Parity Efficiently with Chain of Thought
  28. ICLR 2025U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models
  29. ICLR 2025Understanding Factual Recall in Transformers via Associative Memories
  30. ICLR 2025uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
  31. ICLR 2025When does compositional structure yield compositional generalization? A kernel theory.
  32. ICLR 2025When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
  33. ICLR 2025When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
  34. ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
  35. ICML 2025A Generalization Theory for Zero-Shot Prediction
  36. ICML 2025A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning
  37. ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
  38. ICML 2025A Theory for Conditional Generative Modeling on Multiple Data Sources
  39. ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
  40. ICML 2025A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
  41. ICML 2025A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
  42. ICML 2025A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games
  43. ICML 2025Adversarial Robust Generalization of Graph Neural Networks
  44. ICML 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
  45. ICML 2025Algorithms with Calibrated Machine Learning Predictions
  46. ICML 2025All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance
  47. ICML 2025An analytic theory of creativity in convolutional diffusion models
  48. ICML 2025An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
  49. ICML 2025An Error Analysis of Flow Matching for Deep Generative Modeling
  50. ICML 2025Anytime-Constrained Equilibria in Polynomial Time

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查理论 · learning theory在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "theory-learning-theory"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇理论 · learning theory论文？
共 1,350 篇，按年份分别是 2023 年 86 篇、2024 年 393 篇、2025 年 389 篇、2026 年 482 篇。
NeurIPS 2026 有多少篇理论 · learning theory论文？
NeurIPS 2026 有 112 篇理论 · learning theory论文，上一届是 106 篇。
ICLR 2026 有多少篇理论 · learning theory论文？
ICLR 2026 有 200 篇理论 · learning theory论文，上一届是 147 篇。
ICML 2026 有多少篇理论 · learning theory论文？
ICML 2026 有 170 篇理论 · learning theory论文，上一届是 132 篇。
CVPR 2025 有多少篇理论 · learning theory论文？
CVPR 2025 有 4 篇理论 · learning theory论文，上一届是 1 篇。
哪个会议的理论 · learning theory论文最多？
NeurIPS，2023–2026 年共 540 篇。

「理论与统计」下的其他主题